让分割模型同时学多个医院数据，还能自动适应新模态
U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization
- 用领域门控头统一处理不同医院的医学图像数据
- 在跨机构脑病灶数据上实现新基准性能
- 支持新增影像模态和解剖结构的无缝学习
临床实践中，医学分割数据集常受限且异质，不同机构间存在成像模态、扫描协议和解剖目标的差异。现有深度学习模型难以从这类多样化数据中联合学习，常在泛化性和特定领域知识之间妥协。为此，我们提出一种名为通用调和（U-Harmony）的联合训练方法，可集成至基于深度学习的架构中，采用领域门控头使单一分割模型能同时学习异构数据。通过引入U-Harmony，我们的方法依次对特征分布进行归一化与反归一化，以缓解领域特异性差异，同时保留原始数据集的专有知识。更优的是，该框架支持通用模态适配，可无缝学习新成像模态和解剖类别。在跨机构脑病灶数据集上的大量实验验证了方法的有效性，为真实临床场景下的鲁棒、可扩展3D医学图像分割模型树立了新基准。
原文摘要 · Abstract (English)
In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Existing deep learning models struggle to jointly learn from such diverse data, often sacrificing either generalization or domain-specific knowledge. To overcome these challenges, we propose a joint training method called Universal Harmonization (U-Harmony), which can be integrated into deep learning-based architectures with a domain-gated head, enabling a single segmentation model to learn from heterogeneous datasets simultaneously. By integrating U-Harmony, our approach sequentially normalizes and then denormalizes feature distributions to mitigate domain-specific variations while preserving original dataset-specific knowledge. More appealingly, our framework also supports universal modality adaptation, allowing the seamless learning of new imaging modalities and anatomical classes. Extensive experiments on cross-institutional brain lesion datasets demonstrate the effectiveness of our approach, establishing a new benchmark for robust and adaptable 3D medical image segmentation models in real-world clinical settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。